Model Updated

SoccerTwos.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c53c5186877b1d13fb41a403452cebbabd18bc8706b80baa12f82dc35f20e7
+oid sha256:82c006caca581c4db3d41c322b3c26b6e68920321e0fa2fabd613e238d7107c7
 size 1768747

SoccerTwos/{SoccerTwos-10000020.onnx → SoccerTwos-28499966.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c53c5186877b1d13fb41a403452cebbabd18bc8706b80baa12f82dc35f20e7
+oid sha256:34b9cea6b9c6025ab34bcff4b4a44fac5fa99edd9ce609cbddae572ed160e7a2
 size 1768747

SoccerTwos/{SoccerTwos-10000020.pt → SoccerTwos-28499966.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4eab2d4abb6d0932076d718f425a7b775b94bd6f2806c0aa708b65f7af24c39d
+oid sha256:e9c20fc7ae2caf1ee26f5d000e78ca13e2451dce95996c42d3fed6a1db7f5924
 size 28431689

SoccerTwos/{SoccerTwos-8999899.onnx → SoccerTwos-28999938.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4beac03a7c1d8f5c3d91f3cddd9c1241117ccf637527dd9ff00255ffb29fc1
+oid sha256:9bd6ff4780e2159cfcf1fef682b7ae58c1e03793025a4c299e79e59f1bb834fe
 size 1768747

SoccerTwos/{SoccerTwos-8499970.pt → SoccerTwos-28999938.pt}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2ea0a7fb6116937514ddaad603bcd4bcbdd49259ed9851e8ebd9f6a60f5a2f
-size 28431567
+oid sha256:5ee7140e1d2a7909d4a86c9c538cf7d92acefed1b0a450df6737296bf538d055
+size 28431689

SoccerTwos/{SoccerTwos-8499970.onnx → SoccerTwos-29499973.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feba3bc1706eaa5adb9449a45bad7b571b421e62e2ee13177bb2424d11ea6449
+oid sha256:ea4cb0fbafda902d955e5fe51b38714d8792269cace172f61cbfb3d8a5fe7dea
 size 1768747

SoccerTwos/SoccerTwos-29499973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0154cb53b4039d31b83597612d3a8f70cf41a8c94011c35434473deabfef7bce
+size 28431689

SoccerTwos/{SoccerTwos-9499940.onnx → SoccerTwos-29999821.onnx}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:258d710fc5683a90b6be1dc956631d4be249e5517f77a642a1016f7e1a846ff2
+oid sha256:82c006caca581c4db3d41c322b3c26b6e68920321e0fa2fabd613e238d7107c7
 size 1768747

SoccerTwos/SoccerTwos-29999821.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7b376b73a669601619ad24cffe6576064729eeca9f13cbaa5c878d6499df9ff
+size 28431689

SoccerTwos/SoccerTwos-30000024.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82c006caca581c4db3d41c322b3c26b6e68920321e0fa2fabd613e238d7107c7
+size 1768747

SoccerTwos/SoccerTwos-30000024.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:172025985b1b5a0ff846bc9a5eecba2ff5e7adcecb9752364266dfabdb588ff6
+size 28431689

SoccerTwos/SoccerTwos-8999899.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:35dfa6fa20556ac206927a738b4a5966aad1df4f7c25e0ec641c1db9a9a28dea
-size 28431567

SoccerTwos/SoccerTwos-9499940.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7abb89d57f3ad6e977ad2b8a7a67779618bceecd0c0bffb0bb6ec0e40de3e188
-size 28431567

SoccerTwos/SoccerTwos-9999960.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a2c53c5186877b1d13fb41a403452cebbabd18bc8706b80baa12f82dc35f20e7
-size 1768747

SoccerTwos/SoccerTwos-9999960.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f92693a6b921a732b0e1f6c0b5b4d095f1919caabcb399c2d63d7c91d6cddc5f
-size 28431567

SoccerTwos/checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:329f5729d24630225bbe31382bb4a519f667be7c83d3ce51c40ef6e01371d2cd
+oid sha256:464d41c4b3f4754e750ec8e5a68160891d34b75e8a9e0d22f6bf8dcaafdc2f2b
 size 28430591

SoccerTwos/events.out.tfevents.1678659736.XPS-DESKTOP.34300.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0502029475dbeadeaa32fc884d097cd463a0f30329daba8d773a9099e5c8de9
+size 5139973

SoccerTwos/events.out.tfevents.1678664919.XPS-DESKTOP.23932.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abfa17ba7aae20237cf0924998c73c8d34011e134cc5bf9b97563c7c1e05abbc
+size 5139973

SoccerTwos/events.out.tfevents.1678669400.XPS-DESKTOP.41580.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30f5db0f3b402c3cd1b1b438942349acd4ffe1f2fd89815479dd54cd6534ef5f
+size 5139973

SoccerTwos/events.out.tfevents.1678673844.XPS-DESKTOP.36428.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004ded21a6393c82104600279574d395f2c50da895f13b1eb27d7a8a2b0b2a35
+size 1241

SoccerTwos/events.out.tfevents.1678673863.XPS-DESKTOP.40632.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32115a001ef9695c7633c60ef882054c7d9b83550753d744f0dfb1877148810d
+size 5139973

config.json

@@ -1 +1 @@
-{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0003, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 10000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/windows/SoccerTwos/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}
+{"default_settings": null, "behaviors": {"SoccerTwos": {"trainer_type": "poca", "hyperparameters": {"batch_size": 2048, "buffer_size": 20480, "learning_rate": 0.0001, "beta": 0.005, "epsilon": 0.2, "lambd": 0.95, "num_epoch": 3, "learning_rate_schedule": "constant", "beta_schedule": "constant", "epsilon_schedule": "constant"}, "checkpoint_interval": 500000, "network_settings": {"normalize": false, "hidden_units": 512, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}, "reward_signals": {"extrinsic": {"gamma": 0.99, "strength": 1.0, "network_settings": {"normalize": false, "hidden_units": 128, "num_layers": 2, "vis_encode_type": "simple", "memory": null, "goal_conditioning_type": "hyper", "deterministic": false}}}, "init_path": null, "keep_checkpoints": 5, "even_checkpoints": false, "max_steps": 30000000, "time_horizon": 1000, "summary_freq": 10000, "threaded": false, "self_play": {"save_steps": 50000, "team_change": 200000, "swap_steps": 2000, "window": 10, "play_against_latest_model_ratio": 0.5, "initial_elo": 1200.0}, "behavioral_cloning": null}}, "env_settings": {"env_path": "./training-envs-executables/windows/SoccerTwos/SoccerTwos.exe", "env_args": null, "base_port": 5005, "num_envs": 1, "num_areas": 1, "seed": -1, "max_lifetime_restarts": 10, "restarts_rate_limit_n": 1, "restarts_rate_limit_period_s": 60}, "engine_settings": {"width": 84, "height": 84, "quality_level": 5, "time_scale": 20, "target_frame_rate": -1, "capture_frame_rate": 60, "no_graphics": true}, "environment_parameters": null, "checkpoint_settings": {"run_id": "SoccerTwos", "initialize_from": null, "load_model": false, "resume": true, "force": false, "train_model": false, "inference": false, "results_dir": "results"}, "torch_settings": {"device": null}, "debug": false}

configuration.yaml

@@ -5,7 +5,7 @@ behaviors:
     hyperparameters:
       batch_size: 2048
       buffer_size: 20480
-      learning_rate: 0.0003
+      learning_rate: 0.0001
       beta: 0.005
       epsilon: 0.2
       lambd: 0.95
@@ -37,7 +37,7 @@ behaviors:
     init_path: null
     keep_checkpoints: 5
     even_checkpoints: false
-    max_steps: 10000000
+    max_steps: 30000000
     time_horizon: 1000
     summary_freq: 10000
     threaded: false

run_logs/Player-0.log

@@ -9,7 +9,7 @@ NullGfxDevice:
     Renderer: Null Device
     Vendor:   Unity Technologies
 Begin MonoManager ReloadAssembly
-- Completed reload, in  0.044 seconds
+- Completed reload, in  0.053 seconds
 ERROR: Shader Sprites/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Microsoft Media Foundation video decoding to texture disabled: graphics device is Null, only Direct3D 11 and Direct3D 12 (only on desktop) are supported for hardware-accelerated video decoding.
 ERROR: Shader Sprites/Mask shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
@@ -35,7 +35,7 @@ ERROR: Shader Standard shader is not supported on this GPU (none of subshaders/f
 WARNING: Shader Unsupported: 'Standard' - All subshaders removed
 WARNING: Shader Did you use #pragma only_renderers and omit this platform?
 WARNING: Shader If subshaders removal was intentional, you may have forgotten turning Fallback off?
-UnloadTime: 0.437200 ms
+UnloadTime: 0.380300 ms
 Registered Communicator in Agent.
 ERROR: Shader UI/Default shader is not supported on this GPU (none of subshaders/fallbacks are suitable)
 Setting up 16 worker threads for Enlighten.
@@ -43,7 +43,7 @@ Memory Statistics:
 [ALLOC_TEMP_TLS] TLS Allocator
   StackAllocators : 
     [ALLOC_TEMP_MAIN]
-      Peak usage frame count: [8.0 KB-16.0 KB]: 94120 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [8.0 KB-16.0 KB]: 94129 frames, [2.0 MB-4.0 MB]: 1 frames
       Initial Block Size 4.0 MB
       Current Block Size 4.0 MB
       Peak Allocated Bytes 2.0 MB
@@ -88,12 +88,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 14]
+    [ALLOC_TEMP_Job.Worker 17]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 17]
+    [ALLOC_TEMP_Job.Worker 14]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
@@ -183,12 +183,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 0 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 21]
+    [ALLOC_TEMP_Job.Worker 26]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 26]
+    [ALLOC_TEMP_Job.Worker 21]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
@@ -283,12 +283,12 @@ Memory Statistics:
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 15]
+    [ALLOC_TEMP_Job.Worker 24]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
       Overflow Count 0
-    [ALLOC_TEMP_Job.Worker 24]
+    [ALLOC_TEMP_Job.Worker 15]
       Initial Block Size 256.0 KB
       Current Block Size 256.0 KB
       Peak Allocated Bytes 54 B
@@ -315,16 +315,16 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_DEFAULT_MAIN]
-      Peak usage frame count: [4.0 MB-8.0 MB]: 94121 frames
+      Peak usage frame count: [4.0 MB-8.0 MB]: 94130 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 5.2 MB
+      Peak Allocated memory 5.0 MB
       Peak Large allocation bytes 0 B
     [ALLOC_DEFAULT_THREAD]
-      Peak usage frame count: [16.0 MB-32.0 MB]: 94121 frames
+      Peak usage frame count: [16.0 MB-32.0 MB]: 94130 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
-      Peak Allocated memory 17.3 MB
+      Peak Allocated memory 17.4 MB
       Peak Large allocation bytes 16.0 MB
 [ALLOC_TEMP_JOB_1_FRAME]
   Initial Block Size 2.0 MB
@@ -353,13 +353,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_GFX_MAIN]
-      Peak usage frame count: [32.0 KB-64.0 KB]: 94120 frames, [64.0 KB-128.0 KB]: 1 frames
+      Peak usage frame count: [32.0 KB-64.0 KB]: 94129 frames, [64.0 KB-128.0 KB]: 1 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 65.6 KB
       Peak Large allocation bytes 0 B
     [ALLOC_GFX_THREAD]
-      Peak usage frame count: [128.0 KB-256.0 KB]: 94121 frames
+      Peak usage frame count: [128.0 KB-256.0 KB]: 94130 frames
       Requested Block Size 16.0 MB
       Peak Block count 1
       Peak Allocated memory 173.6 KB
@@ -371,13 +371,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_CACHEOBJECTS_MAIN]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 94121 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 94130 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 0.6 MB
       Peak Large allocation bytes 0 B
     [ALLOC_CACHEOBJECTS_THREAD]
-      Peak usage frame count: [0.5 MB-1.0 MB]: 94120 frames, [2.0 MB-4.0 MB]: 1 frames
+      Peak usage frame count: [0.5 MB-1.0 MB]: 94129 frames, [2.0 MB-4.0 MB]: 1 frames
       Requested Block Size 4.0 MB
       Peak Block count 1
       Peak Allocated memory 3.2 MB
@@ -389,13 +389,13 @@ Memory Statistics:
       Used Block count 1
       Peak Allocated bytes 0.9 MB
     [ALLOC_TYPETREE_MAIN]
-      Peak usage frame count: [0-1.0 KB]: 94121 frames
+      Peak usage frame count: [0-1.0 KB]: 94130 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 1.0 KB
       Peak Large allocation bytes 0 B
     [ALLOC_TYPETREE_THREAD]
-      Peak usage frame count: [1.0 KB-2.0 KB]: 94120 frames, [2.0 KB-4.0 KB]: 1 frames
+      Peak usage frame count: [1.0 KB-2.0 KB]: 94129 frames, [2.0 KB-4.0 KB]: 1 frames
       Requested Block Size 2.0 MB
       Peak Block count 1
       Peak Allocated memory 2.2 KB

run_logs/timers.json

@@ -2,75 +2,75 @@
     "name": "root",
     "gauges": {
         "SoccerTwos.Policy.Entropy.mean": {
-            "value": 1.65379798412323,
-            "min": 1.5997190475463867,
-            "max": 2.0455520153045654,
+            "value": 1.818727970123291,
+            "min": 1.3975187540054321,
+            "max": 1.89814293384552,
             "count": 500
         },
         "SoccerTwos.Policy.Entropy.sum": {
-            "value": 35298.6640625,
-            "min": 29036.767578125,
-            "max": 44927.51953125,
+            "value": 35850.765625,
+            "min": 23942.28125,
+            "max": 46826.0859375,
             "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.mean": {
-            "value": 56.41379310344828,
-            "min": 42.5,
-            "max": 89.22222222222223,
+            "value": 60.0625,
+            "min": 49.208333333333336,
+            "max": 100.09803921568627,
             "count": 500
         },
         "SoccerTwos.Environment.EpisodeLength.sum": {
-            "value": 19632.0,
-            "min": 18576.0,
-            "max": 20872.0,
+            "value": 19220.0,
+            "min": 18340.0,
+            "max": 21384.0,
             "count": 500
         },
         "SoccerTwos.Self-play.ELO.mean": {
-            "value": 1599.1062382168589,
-            "min": 1499.26239615417,
-            "max": 1624.1002401220335,
+            "value": 1652.4354878700447,
+            "min": 1554.4589325483994,
+            "max": 1652.4354878700447,
             "count": 500
         },
         "SoccerTwos.Self-play.ELO.sum": {
-            "value": 278244.48544973345,
-            "min": 163296.68992854227,
-            "max": 348653.65085761645,
+            "value": 264389.67805920716,
+            "min": 165253.45285088127,
+            "max": 320504.00850322016,
             "count": 500
         },
         "SoccerTwos.Step.mean": {
-            "value": 9999960.0,
-            "min": 5009982.0,
-            "max": 9999960.0,
+            "value": 29999821.0,
+            "min": 25009982.0,
+            "max": 29999821.0,
             "count": 500
         },
         "SoccerTwos.Step.sum": {
-            "value": 9999960.0,
-            "min": 5009982.0,
-            "max": 9999960.0,
+            "value": 29999821.0,
+            "min": 25009982.0,
+            "max": 29999821.0,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.mean": {
-            "value": -0.05524757504463196,
-            "min": -0.1280595064163208,
-            "max": 0.07903289794921875,
+            "value": 0.036940816789865494,
+            "min": -0.12315517663955688,
+            "max": 0.07151053100824356,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicBaselineEstimate.sum": {
-            "value": -9.668325424194336,
-            "min": -21.74785041809082,
-            "max": 13.863698959350586,
+            "value": 5.947471618652344,
+            "min": -17.807540893554688,
+            "max": 11.503410339355469,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.mean": {
-            "value": -0.05671698600053787,
-            "min": -0.13550084829330444,
-            "max": 0.08255944401025772,
+            "value": 0.036059051752090454,
+            "min": -0.1222762018442154,
+            "max": 0.07353762537240982,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicValueEstimate.sum": {
-            "value": -9.925472259521484,
-            "min": -22.28644561767578,
-            "max": 13.499122619628906,
+            "value": 5.805507183074951,
+            "min": -18.399658203125,
+            "max": 11.578338623046875,
             "count": 500
         },
         "SoccerTwos.Environment.CumulativeReward.mean": {
@@ -86,27 +86,27 @@
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.mean": {
-            "value": -0.044036573001316616,
-            "min": -0.41315742192729826,
-            "max": 0.30363243173908544,
+            "value": 0.05774658437100997,
+            "min": -0.4279925933590642,
+            "max": 0.30688589189681537,
             "count": 500
         },
         "SoccerTwos.Policy.ExtrinsicReward.sum": {
-            "value": -7.706400275230408,
-            "min": -64.03940039873123,
-            "max": 44.937599897384644,
+            "value": 9.297200083732605,
+            "min": -69.3348001241684,
+            "max": 50.02240037918091,
             "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.mean": {
-            "value": -0.044036573001316616,
-            "min": -0.41315742192729826,
-            "max": 0.30363243173908544,
+            "value": 0.05774658437100997,
+            "min": -0.4279925933590642,
+            "max": 0.30688589189681537,
             "count": 500
         },
         "SoccerTwos.Environment.GroupCumulativeReward.sum": {
-            "value": -7.706400275230408,
-            "min": -64.03940039873123,
-            "max": 44.937599897384644,
+            "value": 9.297200083732605,
+            "min": -69.3348001241684,
+            "max": 50.02240037918091,
             "count": 500
         },
         "SoccerTwos.IsTraining.mean": {
@@ -122,51 +122,51 @@
             "count": 500
         },
         "SoccerTwos.Losses.PolicyLoss.mean": {
-            "value": 0.021202963617785522,
-            "min": 0.009544935117204053,
-            "max": 0.02366057054605335,
+            "value": 0.014192786024553546,
+            "min": 0.01219411081377378,
+            "max": 0.023256745278680078,
             "count": 242
         },
         "SoccerTwos.Losses.PolicyLoss.sum": {
-            "value": 0.021202963617785522,
-            "min": 0.009544935117204053,
-            "max": 0.02366057054605335,
+            "value": 0.014192786024553546,
+            "min": 0.01219411081377378,
+            "max": 0.023256745278680078,
             "count": 242
         },
         "SoccerTwos.Losses.ValueLoss.mean": {
-            "value": 0.10358574613928795,
-            "min": 0.08451338683565458,
-            "max": 0.12328467046221098,
+            "value": 0.11161482160290083,
+            "min": 0.07874111558000246,
+            "max": 0.11438520128528278,
             "count": 242
         },
         "SoccerTwos.Losses.ValueLoss.sum": {
-            "value": 0.10358574613928795,
-            "min": 0.08451338683565458,
-            "max": 0.12328467046221098,
+            "value": 0.11161482160290083,
+            "min": 0.07874111558000246,
+            "max": 0.11438520128528278,
             "count": 242
         },
         "SoccerTwos.Losses.BaselineLoss.mean": {
-            "value": 0.10516337603330612,
-            "min": 0.08548880691329638,
-            "max": 0.1257518952091535,
+            "value": 0.11257703850666682,
+            "min": 0.07900148158272108,
+            "max": 0.11460107788443566,
             "count": 242
         },
         "SoccerTwos.Losses.BaselineLoss.sum": {
-            "value": 0.10516337603330612,
-            "min": 0.08548880691329638,
-            "max": 0.1257518952091535,
+            "value": 0.11257703850666682,
+            "min": 0.07900148158272108,
+            "max": 0.11460107788443566,
             "count": 242
         },
         "SoccerTwos.Policy.LearningRate.mean": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
+            "value": 9.999999999999998e-05,
+            "min": 9.999999999999998e-05,
+            "max": 9.999999999999998e-05,
             "count": 242
         },
         "SoccerTwos.Policy.LearningRate.sum": {
-            "value": 0.0003,
-            "min": 0.0003,
-            "max": 0.0003,
+            "value": 9.999999999999998e-05,
+            "min": 9.999999999999998e-05,
+            "max": 9.999999999999998e-05,
             "count": 242
         },
         "SoccerTwos.Policy.Epsilon.mean": {
@@ -196,7 +196,7 @@
     },
     "metadata": {
         "timer_format_version": "0.1.0",
-        "start_time_seconds": "1678655180",
+        "start_time_seconds": "1678673860",
         "python_version": "3.9.16 | packaged by conda-forge | (main, Feb  1 2023, 21:28:38) [MSC v.1929 64 bit (AMD64)]",
         "command_line_arguments": "C:\\Users\\xps\\Anaconda3\\envs\\drl-hug-u5\\Scripts\\mlagents-learn ./config/poca/SoccerTwos.yaml --env=./training-envs-executables/windows/SoccerTwos/SoccerTwos.exe --run-id=SoccerTwos --no-graphics --resume",
         "mlagents_version": "0.31.0.dev0",
@@ -204,103 +204,103 @@
         "communication_protocol_version": "1.5.0",
         "pytorch_version": "1.13.1",
         "numpy_version": "1.21.2",
-        "end_time_seconds": "1678659654"
+        "end_time_seconds": "1678678365"
     },
-    "total": 4473.5127913999995,
+    "total": 4504.8823232,
     "count": 1,
-    "self": 0.17524949999915407,
+    "self": 0.19206579999990936,
     "children": {
         "run_training.setup": {
-            "total": 0.06630990000000003,
+            "total": 0.06252809999999998,
             "count": 1,
-            "self": 0.06630990000000003
+            "self": 0.06252809999999998
         },
         "TrainerController.start_learning": {
-            "total": 4473.271232,
+            "total": 4504.6277293,
             "count": 1,
-            "self": 4.270477300126913,
+            "self": 4.518602999845825,
             "children": {
                 "TrainerController._reset_env": {
-                    "total": 2.9966998000004024,
+                    "total": 3.3548857000028143,
                     "count": 26,
-                    "self": 2.9966998000004024
+                    "self": 3.3548857000028143
                 },
                 "TrainerController.advance": {
-                    "total": 4465.878635399873,
-                    "count": 346218,
-                    "self": 3.9217136999577633,
+                    "total": 4496.617948200151,
+                    "count": 343717,
+                    "self": 4.042793700359653,
                     "children": {
                         "env_step": {
-                            "total": 3280.9998944999097,
-                            "count": 346218,
-                            "self": 2074.1210437999944,
+                            "total": 3323.9167821999404,
+                            "count": 343717,
+                            "self": 2104.005244100222,
                             "children": {
                                 "SubprocessEnvManager._take_step": {
-                                    "total": 1204.4326893000316,
-                                    "count": 346218,
-                                    "self": 25.3743388999701,
+                                    "total": 1217.2357568998823,
+                                    "count": 343717,
+                                    "self": 26.618170799897143,
                                     "children": {
                                         "TorchPolicy.evaluate": {
-                                            "total": 1179.0583504000615,
-                                            "count": 627484,
-                                            "self": 1179.0583504000615
+                                            "total": 1190.6175860999851,
+                                            "count": 627538,
+                                            "self": 1190.6175860999851
                                         }
                                     }
                                 },
                                 "workers": {
-                                    "total": 2.4461613998837075,
-                                    "count": 346218,
+                                    "total": 2.6757811998358214,
+                                    "count": 343717,
                                     "self": 0.0,
                                     "children": {
                                         "worker_root": {
-                                            "total": 4465.951477699867,
-                                            "count": 346218,
+                                            "total": 4496.714463399915,
+                                            "count": 343717,
                                             "is_parallel": true,
-                                            "self": 2787.5716625999003,
+                                            "self": 2803.423885699962,
                                             "children": {
                                                 "steps_from_proto": {
-                                                    "total": 0.021741099998727975,
+                                                    "total": 0.02242430000007145,
                                                     "count": 52,
                                                     "is_parallel": true,
-                                                    "self": 0.0043293999943334605,
+                                                    "self": 0.004351699996299807,
                                                     "children": {
                                                         "_process_rank_one_or_two_observation": {
-                                                            "total": 0.017411700004394515,
+                                                            "total": 0.018072600003771644,
                                                             "count": 208,
                                                             "is_parallel": true,
-                                                            "self": 0.017411700004394515
+                                                            "self": 0.018072600003771644
                                                         }
                                                     }
                                                 },
                                                 "UnityEnvironment.step": {
-                                                    "total": 1678.358073999968,
-                                                    "count": 346218,
+                                                    "total": 1693.268153399953,
+                                                    "count": 343717,
                                                     "is_parallel": true,
-                                                    "self": 85.32835019983918,
+                                                    "self": 86.35576059978962,
                                                     "children": {
                                                         "UnityEnvironment._generate_step_input": {
-                                                            "total": 64.66652489993018,
-                                                            "count": 346218,
+                                                            "total": 64.43223800010765,
+                                                            "count": 343717,
                                                             "is_parallel": true,
-                                                            "self": 64.66652489993018
+                                                            "self": 64.43223800010765
                                                         },
                                                         "communicator.exchange": {
-                                                            "total": 1265.606581099998,
-                                                            "count": 346218,
+                                                            "total": 1278.1940108999183,
+                                                            "count": 343717,
                                                             "is_parallel": true,
-                                                            "self": 1265.606581099998
+                                                            "self": 1278.1940108999183
                                                         },
                                                         "steps_from_proto": {
-                                                            "total": 262.7566178002005,
-                                                            "count": 692436,
+                                                            "total": 264.28614390013746,
+                                                            "count": 687434,
                                                             "is_parallel": true,
-                                                            "self": 50.712452700117154,
+                                                            "self": 51.1290133007256,
                                                             "children": {
                                                                 "_process_rank_one_or_two_observation": {
-                                                                    "total": 212.04416510008335,
-                                                                    "count": 2769744,
+                                                                    "total": 213.15713059941186,
+                                                                    "count": 2749736,
                                                                     "is_parallel": true,
-                                                                    "self": 212.04416510008335
+                                                                    "self": 213.15713059941186
                                                                 }
                                                             }
                                                         }
@@ -313,31 +313,31 @@
                             }
                         },
                         "trainer_advance": {
-                            "total": 1180.957027200005,
-                            "count": 346218,
-                            "self": 27.727685300063968,
+                            "total": 1168.6583722998507,
+                            "count": 343717,
+                            "self": 29.780961900001557,
                             "children": {
                                 "process_trajectory": {
-                                    "total": 543.4619141999411,
-                                    "count": 346218,
-                                    "self": 542.3257620999414,
+                                    "total": 520.1106167998515,
+                                    "count": 343717,
+                                    "self": 518.9993802998533,
                                     "children": {
                                         "RLTrainer._checkpoint": {
-                                            "total": 1.1361520999998334,
+                                            "total": 1.111236499998256,
                                             "count": 10,
-                                            "self": 1.1361520999998334
+                                            "self": 1.111236499998256
                                         }
                                     }
                                 },
                                 "_update_policy": {
-                                    "total": 609.7674277,
+                                    "total": 618.7667935999976,
                                     "count": 242,
-                                    "self": 385.8467676000039,
+                                    "self": 393.2692417000187,
                                     "children": {
                                         "TorchPOCAOptimizer.update": {
-                                            "total": 223.92066009999607,
+                                            "total": 225.49755189997893,
                                             "count": 7260,
-                                            "self": 223.92066009999607
+                                            "self": 225.49755189997893
                                         }
                                     }
                                 }
@@ -346,19 +346,19 @@
                     }
                 },
                 "trainer_threads": {
-                    "total": 5.000001692678779e-07,
+                    "total": 4.000003173132427e-07,
                     "count": 1,
-                    "self": 5.000001692678779e-07
+                    "self": 4.000003173132427e-07
                 },
                 "TrainerController._save_models": {
-                    "total": 0.1254189999999653,
+                    "total": 0.13629200000013952,
                     "count": 1,
-                    "self": 0.004603999999744701,
+                    "self": 0.02065960000072664,
                     "children": {
                         "RLTrainer._checkpoint": {
-                            "total": 0.12081500000022061,
+                            "total": 0.11563239999941288,
                             "count": 1,
-                            "self": 0.12081500000022061
+                            "self": 0.11563239999941288
                         }
                     }
                 }

run_logs/training_status.json

@@ -2,59 +2,59 @@
     "SoccerTwos": {
         "checkpoints": [
             {
-                "steps": 8499970,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499970.onnx",
+                "steps": 28499966,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28499966.onnx",
                 "reward": 0.0,
-                "creation_time": 1678658300.0205026,
+                "creation_time": 1678677006.443449,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8499970.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28499966.pt"
                 ]
             },
             {
-                "steps": 8999899,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999899.onnx",
+                "steps": 28999938,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28999938.onnx",
                 "reward": 0.0,
-                "creation_time": 1678658741.8437095,
+                "creation_time": 1678677465.761777,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-8999899.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-28999938.pt"
                 ]
             },
             {
-                "steps": 9499940,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499940.onnx",
+                "steps": 29499973,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29499973.onnx",
                 "reward": 0.0,
-                "creation_time": 1678659188.945941,
+                "creation_time": 1678677917.3935664,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9499940.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29499973.pt"
                 ]
             },
             {
-                "steps": 9999960,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999960.onnx",
+                "steps": 29999821,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29999821.onnx",
                 "reward": 0.0,
-                "creation_time": 1678659653.7992427,
+                "creation_time": 1678678365.4933496,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-9999960.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-29999821.pt"
                 ]
             },
             {
-                "steps": 10000020,
-                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000020.onnx",
+                "steps": 30000024,
+                "file_path": "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30000024.onnx",
                 "reward": 0.0,
-                "creation_time": 1678659653.930643,
+                "creation_time": 1678678365.620856,
                 "auxillary_file_paths": [
-                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000020.pt"
+                    "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30000024.pt"
                 ]
             }
         ],
-        "elo": 1598.600891125928,
+        "elo": 1653.491829913033,
         "final_checkpoint": {
-            "steps": 10000020,
+            "steps": 30000024,
             "file_path": "results\\SoccerTwos\\SoccerTwos.onnx",
             "reward": 0.0,
-            "creation_time": 1678659653.930643,
+            "creation_time": 1678678365.620856,
             "auxillary_file_paths": [
-                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-10000020.pt"
+                "results\\SoccerTwos\\SoccerTwos\\SoccerTwos-30000024.pt"
             ]
         }
     },